Symbioza — Claude Code MCP server: what it does, how to install
Runs containerized GPU jobs under a strict budget ceiling and retrieves generated files. Useful for fine-tuning models and batch inference without surprise bills.
claude mcp add --transport http symbioza https://symbioza.dev/mcpWhat Symbioza does
Symbioza links your coding assistant to cloud GPU nodes through a remote HTTP endpoint. The agent specifies a container image and an execution command. A strict spending ceiling applies to every run. Hardware provisioning and artifact retrieval happen automatically.
The server provides nine tools, including estimateExecution, submitJob, and getArtifact. You can inspect projected runtimes and hourly rates before spending money. Estimation is completely free.
Authentication relies on browser OAuth. No static API token is required. Submissions will fail if your account balance is zero, so you must add funds before dispatching compute.
What it helps with
- Cap cloud GPU spending with a hard financial cutoff
- Preview training runtime and expenses prior to execution
- Launch containerized model evaluations directly from coding agents
- Download generated checkpoints and logs after a remote run completes
Example prompts for the agent
- Estimate the cost to run an evaluation job in
pytorch/pytorch:latestbefore starting compute. - Check the progress of my Symbioza job and download the saved weights once finished.
- Draft the container arguments for batch inference on Symbioza without submitting yet.
How to install Symbioza
Platform CLI: remote server
claude mcp add --transport http symbioza https://symbioza.dev/mcpPlatform CLI: remote server
codex mcp add symbioza --url https://symbioza.dev/mcpConfig file
{
"mcpServers": {
"symbioza": {
"url": "https://symbioza.dev/mcp"
}
}
}Config file
{
"servers": {
"symbioza": {
"type": "http",
"url": "https://symbioza.dev/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http symbioza https://symbioza.dev/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Symbioza
How to install Symbioza in Claude Code?
Run claude mcp add --transport http symbioza https://symbioza.dev/mcp in your terminal. Next, trigger /mcp in your agent session and finish the OAuth sign-in in your browser.
What does the Symbioza MCP server do?
It connects coding assistants to cloud GPUs for training, evaluation, and batch workloads. Compute stops strictly at your specified budget ceiling, returning the generated files.
Do I need an API key to run Symbioza?
No API key is required. The server connects via streamable HTTP and signs in through browser-based OAuth.
